We are IntechOpen, the world s leading publisher of Open Access books Built by scientists, for scientists. International authors and editors

Transcription

1 We are IntechOpen, the world s leading publisher of Open Access books Built by scientists, for scientists 3, , M Open access books available International authors and editors Downloads Our authors are among the 154 Countries delivered to TOP 1% most cited scientists 12.2% Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science Core Collection (BKCI) Interested in publishing with us? Contact book.department@intechopen.com Numbers displayed above are based on latest data collected. For more information visit

2 5 Digital Restoration by Denoising and Binarization of Historical Manuscripts Images Dimitrios Ventzas 1, Nikolaos Ntogas 2 and Maria-Malamo Ventza 3 1 Department of Computer Science and Telecommunications, Technological Educational Institute of Larissa, 2 Computer Science Technology & Telecommunications, TEI of Larisa, 3 University of Western Greece, Dpt of Cultural Resources & New Technologies, Greece 1. Introduction This chapter deals with digital restoration, preservation, and data base storage of historical manuscripts images. It focuses on restoration techniques and binarization methods combined with image processing applied on document images for text - background enhancement and discrimination. Sequential image processing procedures are applied for image refinement and enhancement on quality class categorized images. Research results on historical (i.e. Byzantine, old newspapers, etc) manuscripts are presented. The historical documents images acquisition types / formats are raw data files or JPG, video, i.e. frames at a speed, storage / transfer types / format e.g. lossless / lossy compressed files, standard print formats, reduced by calibration with a flat-field image. Rarely different areas of a large image are shot with overlapping in order to create a panorama; image alignment/stitching include key point detection feature matching, geometric registration and global registration. Among libraries, and museums, there are old documents preserved in storage areas. Many of these documents are considered as quite important for national heritage, see fig. 1. Their efficient preservation and unconditional exploitation to wider public even through the internet is a trend in modern archaeology. In image acquisition by digital cameras, see fig. 1, no flash lights are used, since the light could permanently degrade the documents colours and results in poor quality images. Our work concentrates on two basic techniques used for image enhancement and restoration, denoising and binarization. Denoising refers to the removal of noise on the image and binarization refers to the conversion of a grayscale image to binary. Binarization by thresholding converts the grayscale document image to binary, by changing the foreground pixels (text characters) to black and background pixels to white. Image thresholding obtains a resulting binary image in black and white, easily stored in computer, while retaining all the basic characteristics of the original image.

3 74 Advanced Image Acquisition, Processing Techniques and Applications All algorithms and ideas in this chapter are applied and tested to old pages photographically acquired from historical books and manuscripts called Codices, from the Holy Monastery of Dousiko, Pylh, near Meteora, Trikala, see Fig. 1. Fig. 1. Taking photos of Byzantine manuscript from Dousiko Byzantine Holy Monastery, Pylh, Greece 2. Document image acquisition Document raw image acquisition (sharpness, resolution and transfer function curves) by camera, video or scanner highly depends on machine vision systems (Boyle 1988, Davies, 1990) and the combined effects of viewing distance / angle from the eye, depth of field, optimum aperture, lens sharpness. camera misalignment, aperture, lens characteristics, polarizing filters, diffraction, light and illumination types, focus, zoom, scaling and sharpness control, long exposure noise reduction, optimal intelligence and minimally processing sensors (Adams, 1995). We acquire old documents images by a digital field camera (a CMOS technology SLR CANON 1.8II with a 50 mm lens) with high resolution ratio (4,368 x 2,904 pixels a total of 12,684,672 recorded pixels (12 Mbytes storage space), and stored in computer and compressed for storage minimization and sensors size 24 mm x 36mm (Canon 2007). Raw images usually have 12 bits colour information per pixel. Image editing software uses 8 bits, or 16 bits. The 12 bits per pixel data from a RAW file is more accurate than the 8 bit format of a.jpg, but the.jpg 8 bits contain various corrections. For textual images published on the web site, enlarged and printed to larger dimensions than 10 x 8 compression may provide inadequate quality. Raw format allows us to correct defects (under/over exposure, colour balance, etc). Raw/.jpg images differ in that we make the adjustment before/after non-linear corrections (γ- correction) i.e. before/after saving it as a.jpg, TIFF, PSD files.

4 Digital Restoration by Denoising and Binarization of Historical Manuscripts Images 75 Fig. 2a. Spherical error (lens chromatic aberrations), i.e. optical imperfections (different bending of light at different wavelengths), the inability of spherical surfaces to provide clear images over large fields of view, changes in focus for light rays that don't pass through the center of the lens, etc (Ren, 2006). Fig. 2b. Lenses inaccuracies - Sine pattern with lens degradation and low to high spatial frequencies variations. Sharpness boundaries between zones of different tones or colors. Signal processing varies with image content (feature contrast) and a camera's ability to render fine detail (texture), i.e., low contrast, high spatial frequency image content. Spatial frequency response is related to total image quality resolution and tonal response. Log f- contrast is sensitive to noise. Sensitivity to sharpening decreases and sensitivity to noise reduction increases from top (most contrast) to bottom (least contrast). Tone photos and correct radial exposure and brightness should be calibrated. SQF (subjective quality factor) is a measure of perceived print sharpness that incorporates the contrast sensitivity function (CSF) of the human eye (Legge, 1985). Retouche software filters, focus and control sharpness without edge lines or artifacts, while color correction software, master exposure compensation, white balance corrector that correct miscoloration in photos caused by any light source (Papamarkos, 2001). Dynamic or exposure range of cameras and scanners is the range of tones over which a camera responds and over which noise remains under a specified level; log exposure is proportional to optical density. Digital cameras output may not follow an exact gamma (exponential) curve (confusion factor), a tone reproduction curve ("S" curve) is superposed on the gamma curve to boost visual contrast without sacrificing dynamic range in middle tones while reducing it in highlights and shadows. Resolution is the ability to resolve fine detail (ppi or dpi).

5 76 Advanced Image Acquisition, Processing Techniques and Applications Good image Bad Image No distortion Barrel Pincushion Geometry Fig. 3. Geometric errors of lenses or images displays Aberrations are chromatic (longitudinal / lateral), coma, astigmatism and curvature of field degrade lens performance and cause focus on different image planes, color fringing due magnification differences with wavelength, see fig. 2. Geometric or perspective (radial lens) distortion have two forms, barrel and pincushion, see fig. 3. Distortion can detect vertical and horizontal lines in extreme wide angle, telephoto and zoom lenses. Highly distorted images are a special case. The ability of the eye to resolve detail is known as visual acuity. The normal human eye can distinguish patterns of alternating black and white lines with a feature size as small as one minute of an arc (1/60 degree or π/(60*180) = radians). A pattern of higher spatial frequency in larger prints, would appear pure gray, low contrast patterns at the maximum spatial frequency will also appear gray. The human eye and brain have a limited ability to discern tonal values, and to analyze large numbers of images simultaneously; it is more qualitative than quantitative. Wavelength (color) psychophysics influences text vision, especially in low-vision conditions. Photopic / scotopic conditions, photoreceptor disorders, characters near the acuity limit, lower luminance, wavelength effects, spectral sensitivities, light scatter or absorption result in depressed / optimal performance in the red, blue / green, gray regions. Eyes differentiate in vertical and horizontal banding. Eyes are wired to recognize differences in vertical and horizontal banding, while the recorded images appear arranged in diagonal arrays. Noise tends to be most visible at medium spatial (actually angular) frequencies where the eye's Contrast Sensitivity Function is large. 3. Image background - foreground In foreground / background analysis, the goal is objects separation and cleaning. Poor contrast between foreground and background characters exists in transparent texts. A text or object within an image viewed dark in color and placed on a light background, exhibits histogram with a good bi-modal distribution, see fig. 4, 5. One peak represents the

6 Digital Restoration by Denoising and Binarization of Historical Manuscripts Images 77 object pixels, one represents the background (Kapur, 1985), see fig. 5. Significant incident illumination gradient across the image blurs out the histogram information. The histogram is altered by many image enhancement operators, mainly the contrast stretching and histogram equalization. Contrast stretching improves contrast. High peaks at the end of the histogram, suggest high intensity and contrast colors. Image statistics calculate histogram, mean color values, standard deviation, median, histogram shape matching, histogram based image segmentation, histogram equalization, etc for each color channel in RGB, HSL, YCbCr color space. Vertical - Horizontal Intensity statistics provide information about vertical - horizontal distribution of pixel intensities and is used to locate objects, centers, etc. Picture segmentation maximizes the separability of resultant classes (Yanowitz, 1989). (a) Fig. 4. Foreground / background analysis (b) Fig. 5. Histogram of relative log scene luminance range Because the dynamic range of the original scene is substantially larger than this, a subset of the image data must be selected. Different results are obtained depending on whether the foreground or background region of the image is selected. Background could be complex and inhomogeneous, while segmentation, ratio foreground / background contrast comparison, classification of large background regions optimize results, see fig. 6. Very low-contrast texts are detrimental to readability and identifiability, because the background may show large variations in luminance (Knoblauch, 1991). While backgrounds (culture, wave, plain) are uniform, the text is not. A common text area contains 23% of text pixels.

7 78 Advanced Image Acquisition, Processing Techniques and Applications Fig. 6. Various quality old paper background textures in old documents, see App Histogram analysis Image statistics parameters and transformation include character features, font information, size, mean-square error, position, dimension and shape, area, gravity point, number of work pieces, correlation, clustering, connection characteristics, ROI, min/max, average/deviation/skewness, column / row location, rms pixel values, etc, see fig. 7, 8, 9, 10, 11. Image color spaces offer flexibility on image processing, i.e. the HLS space has advantages since saturation is low for black/white pixels, brightness is independent of the saturation and freedom of choice to brightness, luminance or lightness function; saturation values are easily compared Fig. 7. Horizontal/vertical cross intensities

8 Digital Restoration by Denoising and Binarization of Historical Manuscripts Images 79 Fig. 8. Horizontal/vertical histogram projections Histograms and noise analysis: The black (background) histogram contains pixel levels for the entire ROI. Sharpening may cause extra bumps to appear in the black histogram. Histogram logarithmic scale improve analysis Fig. 9. Intensity Histogram with 3 classes of pixels

9 80 Advanced Image Acquisition, Processing Techniques and Applications Fig. 10. A CMYK color space is smaller than the monitor RGB color space. Physical display limitations reduce CMYK colors displayed Fig. 11. Hue histogram. The reds and violets are separated by a large discontinuity 5. Color processing When raw RGB data are used without color balance compensation we get incorrect color result, see fig. 12, 13. Soft proofing process minimizes visible color differences, while PDF/X- 4 standard provides a framework that enables colored elements can be reproduced well on different output devices and media. Color (miscoloration) correction software and white balance corrector includes scalar or vectorial processes. The color ratios (R/G) can be especially useful for diagnosing uneven color response.

10 Digital Restoration by Denoising and Binarization of Historical Manuscripts Images 81 Original Image Lightness adjustment Hue (red = -180) Saturation Color balance Contrast Changing lower Threshold limit Changing upper Threshold limit

11 82 Advanced Image Acquisition, Processing Techniques and Applications Level Curve software Desaturation RGB Equalize RGB decomposition White Balance Stretch Contrast Fig. 12. Signal processing filters Brightness 0% raw image 100 % saturation Colour (RGB / YMC) 0% raw image 100 %

12 Digital Restoration by Denoising and Binarization of Historical Manuscripts Images 83 Raw Y G Red Fig. 13. Saturation enhancement - Text in different color spaces (Hunt, 2001) All achieved image deformations are artificial but they are used in understanding or inversion restoration of distorted images, e.g. scanned thick bound documents (Zhang, 2001), see fig. 14. Warp occurs in words, location, shape, shade and orientation. Defocus filter applies a Gaussian blur to the image, making it less clear. Other filters reproduce the effect of aging in old, traditional black-and-white photographs, toned with shades of brown, see fig. 15. To achieve this effect, the filter desaturates the image, reduces brightness and contrast, modifies the color balance and marks the image with spots, see fig. 14. Blinds filter Curve bend filter Emboss filter Erase Every Other row Engrave filter Lens Distortion filter

13 84 Advanced Image Acquisition, Processing Techniques and Applications Newsprint filter Page curl filter Shift filter Ripple filter Value Propagate Filter Video filter Filter waves filter Whirl and Pinch filter Wind filter Fig. 14. Distorted images Distortion

14 Digital Restoration by Denoising and Binarization of Historical Manuscripts Images 85 Old photo filter gives an old photo, blurred with brown shade, spots, jagged border Fig. 15. Maturing old images or stains on images Coffee stain filter adds / subtracts realistic looking stains randomly spread out Images sharpen, shifted horizontally / vertically and fused Fig. 16. Images fusion techniques Images sharpen, shifted horizontally/vertically, rotated and fused The apply canvas and the weave filter applies an artist's canvas-like or weave effect with parameters direction, light source, apparent depth. Clothify filter adds a cloth-like texture with parameters azimuth, elevation, depth). Impressionist and Oilify filter include cubism and gives image the look of a painting with parameters overlay, scale, texture, graininess of the texture, relief, brush, luminosity, gamma correction, mid tones brightens/darkens, aspect ratio, directions, color noise, background. The cartoon filter is similar to a black felt pen drawing subsequently shaded with color. This is achieved by darkening areas that are already distinctly darker than their neighbourhood with parameters lines thinner or thicker, darker and sharper. The predator filter effect makes the image/selection look something like a thermogram. This will reduce the image to edges in a few basic (red, green, blue and gray) colors on a dark background. Photocopy filter makes the image like a black and white photocopy. Soft glow filter applied lights the image with a soft glow diffuse effect, see fig. 17.

15 86 Advanced Image Acquisition, Processing Techniques and Applications 6. Layers fusion Certain data fusion techniques of complementary spatial and spectral resolution characteristics produce enhanced observations, see fig. 16. Dual image point processing maps two pixel brightnesses, one from each image, to an output image by the overlay or the composite operation that merges unrelated objects from two images; this is done on a per band basis. The images are identical scenes, but acquired at different times and spectral filters. An alpha channel represents the transparency of the image (D Zmura, 1997). The Threshold Alpha command converts semi-transparent areas of the active layer into completely transparent or completely opaque areas. It only works on layers of RGB images which have an alpha channel. The transparency transition is abrupt. Composition refers to the merging of two or more distinct objects into a new compound object with new functionality. A single object image is processed to extract object features, modify some of the features, and then merge the modified object back. Image processing techniques include skewed documents correction (Kavallieratou, 1999). Fig. 17. Artistic effects assist to optimal presentation or understanding of wear and image degradation 7. Image text degradation by noise Digital camera images with excessive noise reduction will have an unusually rapid falloff of the noise spectrum. The pixel noise is highly visible; it wouldn't be suitable for portraits and other high quality work, but it would be acceptable when a grainy look is tolerated. Temporal noise is the random difference between otherwise identical images: N temporal = Noise(Image 1 -Image 2 ) / 2; dividing by the square root of 2 scales temporal noise to be the same as noise measured in an individual image. Noise will be worse for higher contrast cameras, affected by the gamma encoding. Gradual illumination nonuniformities should be removed from the noise results. Noise is largest in the dark areas because of gamma encoding. Noise corrupts the images as additive /multiplicative Gaussian, uniform, speckle noise and complex signal dependent noise, salt and pepper with standard deviations (σ=15.0 σ =2.5); filters reduce them to σ=2.0 σ=0.5 respectively). Combinations of noise type, amount, etc corrupt images totally, partially or locally. The documents images are classified into six distinct image categories / conditions, see fig. 18: 1. Acceptable images that are in good condition of camera acquisition and paper 2. Images that present spots, stains, smears, scratches, damages or smudges 3. Images with shadows and wrinkles (Blinn, 1978) caused by:

16 Digital Restoration by Denoising and Binarization of Historical Manuscripts Images High humidity over the years, fragile paper or 3.2 Bad / non uniform illumination and background 3.3 Aging paper colours deterioration and brightness degradation 4. Transparent or oily page or ink wet, seeking / visible from the other side 5. Thin / thick / consistent stroke pen width texts, multiple touching characters 6. Badly blurred or missing ink broken characters with holes or light handwriting 7. Characters with different colours (e.g. red) ink, poor quality of ink Documents with poor quality paper, fragile, etc. The brightness of the aging paper has deteriorated colours over the years. Poor contrast between foreground and background characters. Documents condition, poor quality of ink, broken characters, characters with holes or light handwriting. Ink wet paper with characters visible both sides of paper. Dirty documents with High humidity over various sizes or colours the years cause of spots, stains, smears wrinkles to the paper. or smudges. Image acquisition problems illumination, types of light, non uniformity, low contrast, etc. Fig. 18. Description of problems appeared and examined on Byzantine documents 7.1 Noise on images Randomization (%) represents the percentage of noise affected pixels. A normal distribution of noise means, that only slight noise is added to the most pixels in the affected area, while less pixels are affected by more extreme values. Noise may be additive (uncorrelated) or multiplicative (correlated - also known as speckle noise), repetitive. For wide band and high-pass noise the summation is quite linear while for low-pass noise no summation needed. Hue noise changes the color (strong /weak hue variation) of the pixels in a random pattern; noise varies by saturation or brightness of scattered pixels.

17 88 Advanced Image Acquisition, Processing Techniques and Applications Fig. 19. Noise spectrum Fig. 20. Antialiased images Fig. 21. Sharpened images Artifacts, noise contamination, see fig. 19, edges, sharp transitions, edge blurring, saturation effect on bright / dark text scenes, high corruption, etc. appear for signal above the Nyquist frequency in the digital sensor. Color aliasing and Moire fringing is a type of aliasing, see fig. 20. Noise in digital sensors tends to have the greatest impact in dark regions. The larger the image (the greater the magnification), the more important noise becomes. Color quantization error cause false colours and contours. Analog-to-digital image conversion and image sample / capture rate limitations suggest the highest spatial frequency, Nyquist frequency f N = 1/(2 * pixel spacing); the design of antialiasing (lowpass) filters always involves a trade off that compromises sharpness. Antialias filter reduces or reverses alias effects, jaggies. Antialiasing produces smoother curves by adjusting the boundary between the background and the pixel region that is being antialiased; pixel intensities or opacities are changed for a smoother transition to the background. Lateral Chromatic Aberration (LCA), or color fringing, is visible on tangential edge boundaries.

18 Digital Restoration by Denoising and Binarization of Historical Manuscripts Images 89 The HSV Noise filter creates noise in the HSV active layer The Hurl filter The RGB Noise Slur Filter effect changes each filter adds noise melts the image affected pixel to a to a layer normally downwards random color distributed The spread filter swaps each pixel with randomly chosen pixel Fig. 22. Color spaces filters Out-of-focus photographs and most digitized images often need a sharpness correction. To prevent color distortion while sharpening, we decompose our image to HSV and work only on value, see fig. 22. So we protect areas of smooth tonal transition from sharpening, see fig. 23, 24. In an image with some blur we sharpen by applying some more blur: the intensity variation will be more gradual. We subtract the blurredness intensity from the intensity of the image and get the red curve, which is more abrupt: contrast and sharpness are increased. If blurring is important, this dip is very deep; the result of the subtraction can be negative, and a complementary color stripe will appear along the contrast, or a black halo around a star on the light background of a nebula (black eye effect), see fig. 21. Despeckle removes small isolated defects Red Eye Removal filter Sharpen Unsharp mask filter Fig. 23. Edges on Images (Ventzas, 1994) Physical vs image contours are often very different. A physical edge of the image might yield practically no contour, while a shadow casts a clear image virtual contour where there in fact is no physical edge.

19 90 Advanced Image Acquisition, Processing Techniques and Applications Negative on Difference of Gaussians Neon filter detects edges and gives them a bright neon effect Sobel's filter detects horizontal and vertical edges separately on a scaled image Fig. 24. Grayscale edge detection and preserving algorithms create contours around objects 8. Denoising Denoising filtering methods are in spatial or in frequency domain (Motwani, 2004). Filters are also subdivided to linear and non-linear filters. Many types of filters exist. We concentrate in three filters in spatial domain (mean, median and wiener) with various windows sizes and two filters in frequency domain (Butterworth and Gaussian), see fig Time domain processing Mean filter: The intensity of every pixel in the image is replaced with the averaged value of intensity of its neighbour pixels. 1 Iij (, ) Ixy (, ) M ( xy, ) N where M the number of pixels in the neighbourhood N. Median Filter: This is a non linear filter. If A a1, a2, a3,... an and a1 a2 a3... an R an 1,if n is odd 2 median( A) 1 an a n,if n is even 2 2 n 1 2 Median is a lower rms error filter and remove impulse noise spikes.

20 Digital Restoration by Denoising and Binarization of Historical Manuscripts Images 91 Noise Median Box filters Wiener filter: Wiener filter, known as minimum mean square error filter, is an adaptive linear filter, applied to an image locally, by taking into account the local image variance. When the variance in an image is large the Wiener filter results in light local smoothing, while when the variance is small, it gives an improved local smoothing. Linear filtering in spatial domain is performed by applying a filter with a weighted sum of neighbouring pixels. Filtering is achieved by convolution or correlation kernel rotated by 180 o. 8.2 Blur filter The motion blur filter creates a movement blur, the simple blur filter produces an out of focus camera effect, the IIR and selective Gaussian blur sets its value to the average of a radius; the blur can be set to act in one direction or above a difference threshold, so contrasts are preserved (blur a background and not foreground) and add depth, see fig. 27. The blur tool is used to soften tile seams in images used in tiled backgrounds. Convolution filtering reduces the effects of noise in images or sharpens the detail in blurred images. The selection of the weights determines the nature of the filtering action (high-pass, low-pass). There are several blurring filter kernel: Fig. 25. The Box filter Fig. 26. Bartlett filter

21 92 Advanced Image Acquisition, Processing Techniques and Applications The Box filter is simple, but Bartlett and Gaussian filters produce better blurring, see fig. 25. Bartlett filter pixels to the center are weighted more heavily than pixels away, see fig. 26. original motion blur IIR Gauss blur Fractal filter Rippling filter Fig. 27. Blur filters 8.3 Frequency domain processing Image spatial frequency is measured horizontally, vertically or at any diagonal. DCT/IDCT is better at compactly representing very small images (Gonzalez, 2002, Sonka, 1998). Butterworth Low Pass Filter Huv (, ) [ Duv (, )/ D0 ] n where D 0 is a specific non negative quantity, and D(u,v) it the distance from point (u,v) to the centre of the frequency rectangle, see fig. 28. Gaussian Low Pass Filter (bell curved kernel). D 2 ( u, v)/2 2 Huv (, ) e where D(u,v) it the distance from the origin of the Fourier transform Fig. 28. Ideal, Butterworth and Gaussian low pass filters and corresponding image effects

22 Digital Restoration by Denoising and Binarization of Historical Manuscripts Images 93 The Gaussian filter is separable, and can be split into horizontal /vertical passes. We can filter bright portions, downsample, horizontal and vertical blur and accumulate. By skipping the high-pass filter, we soften the entire image (anti-aliasing). 8.4 Non linear filtering Filters are linear or nonlinear. The linear takes into consideration only the relative position in kernel, and remains constant throughout the whole image filtering. Nonlinear filters are relative to the target pixel and the coefficients are calculated as a function of local variations of the signal. In the linear filter class, average and Gaussian filters are often used. Among the nonlinear filters, the median filter is popular. A selective blurring filter is often used, which emphases the pixels with similar intensity to the target pixel. A bilateral filter is an edge preserving technique being widely used in image processing. Comparing it to the selective blurring filter, it takes into account intensity and spatial similarity with a uniform or Gaussian kernel. Fig. 29. The image is linearized, the pixel levels are adjusted to remove the camera gamma encoding Linear image processing assumes linear luminance. Images are frequently gamma encoded, in the srgb color space, so luminance is not linear. To apply a linear filter, we must gamma decode the values, and if resampling, we must gamma decode, resample, then gamma encode, see fig. 29. The magnitude squared is an enhancement operation, the Phase operation is phase enhancement, quantizing an image on logarithmic rather than linear scale (human eye has a logarithmic intensity response) results in logarithmic enhancement. Noisy image Gaussian Median Midrange Filtered Ideal filter Fig. 30. Filters responses In low level image processing, for shape and edge detection we differentiate filters performance in cases of high noise compared to small noise conditions, see fig. 30. Nonnegative filters do not introduce overshoot or ringing artifacts. Other temporal/spatial/ frequency averaging filters are the non-liner diffusion, the shock, the inverse scale space

23 94 Advanced Image Acquisition, Processing Techniques and Applications filter, reconstruction filter, Brickwall, Tent, BSpline filters. Resampling, decimation, interpolation decreases/increases the sampling rate. In photography, a variety of interpolation filters exist, such as nearest neighbour averaging, bilinear, bicubic interpolation for higher resampling ratios. Reconstruction filters reconstruct an image from a collection of wavelet coefficients. original image grayscale after mean filter 5-by-5 after median filter 7-by-7 after max filter 5-by-5 after min filter 5-by-5 after wiener filter 7-by-7 Table 1. Filtering on Byzantine documents 9. Denoising results a. Filtering improves the image quality, and prepares it for binarization b. Spatial domain filtering uses Mean, Median and Wiener filters c. Frequency domain filtering uses the Butterworth and Gaussian low pass filters d. The paper condition and lighting conditions is an important factor Type of filter Performance High Noise Small Noise Gaussian poor same good bad good Median very good and same with Salt & Pepper Midrange bad bad bad Gradient inverse weighed good very bad with Salt & Pepper noise K-nearest neighbor bad bad bad Table 2. Filters performance Researchers investigated the combined effects of high and low pass filtering on both letters and noise (noise filtered but letters unfiltered, etc). Averaged thresholds showed that for a given noise, unfiltered letters (the sum of the high- and low-pass letters) led to better recognition than either component filtered letter alone. High-pass letters led to better performance than unfiltered letters in low-pass noise. Cleaning up scanned text pages from old manuscripts is achieved through Dilation Erosion, Opening and Closing techniques of raw or negative images. We look on how to clean up isolated noise dots without removing dots that are part of characters, by using bwareaopen, bwlabel and regionprops to highlight the pixels that were removed and logical operators (logical AND of the dilated characters with the pixels removed or logical OR) to restore the removed pixels. We suggest the use of morphological reconstruction to get all the pixels connected to the overlapping pixels. Thinning and cropping could lead to segmented characters that include parts (remains) of other neighboring print objects, while skeletonization displaces junctions, and short false branches occur. Thinning of thick binary

24 Digital Restoration by Denoising and Binarization of Historical Manuscripts Images 95 images reduces shape outlines, while different thinning rules optimize edge noise, remove, add or move spurious noise and edges, see fig. 31. Dilate filter Erode noise Convolution kernel (5x5 or 3x3) (sharpen, blur, edge, enhance, detect, emboss, etc) Emboss filter Displacement filter Illusion Filter Fractal trace filter Seamless filter Warp filter Fig. 31. Convolution filters / Erosion / Dilation on Images

25 96 Advanced Image Acquisition, Processing Techniques and Applications Warp filter masks an image to protect / wrap / unwrap it against filter action (steps, smears, blackens, displaces, dithers, swirls, scatters, etc), see fig. 31. Fig. 32. Whirl: Using gradient to bend / unbend a text Fig. 33. Convolution filters 9.1 Image enhancement Image Enhancement of degraded text includes add borders, crop an image, rescale amplitude, equalize / match histogram, modify / apply multi-band (RGB), or color-cube / generic lookup table, dithering, offsets, pixel point processing (pixel inverting), thresholding (binary contrast enhancement), segmentation with / without a priori font information, retouche light, radial exposure and brightness, handwritten characters clarification (Gatos, 2004), texture unsharp masking, edge enhancement, etc (Gupta, 2007), see fig. 34. Retouching filters, controls focus and sharpness without artifacts, with color correction, exposure compensation, white balance corrector for miscoloration caused by light source,

26 Digital Restoration by Denoising and Binarization of Historical Manuscripts Images 97 master transparency like GIFs with transparent backgrounds, master contrast, saturation, correct camera lens distortions, master noise filtering, photos tone, etc. Historical manuscripts image processing consists of the following five stages: Image acquisition by a digital camera offers inherent advantages, i.e. produces less noise, with high resolution and image prepared for binarization. Image preparation converts the original raw image format into TIFF /JPEG file format for memory saving and minimal computational effort. Cropping, removing invisible and irrelevant information and converting to grayscale are necessary steps before denoising and binarization. Denoising is derived by comparing Mean, Median and Wiener filters in spatial domain and Gaussian and Butterworth filters in the frequency domain. Thresholding is applied by global (Otsu s) and local (Niblack, Sauvola, Bernsen) thresholding techniques to previous stages resulting, filtered images. Refinement procedure is applied on the binarized image, based on erosion and dilation, such that the obtained image has its characteristics further clarified in the texture and foreground compared with the background area. Cleaning and enhancing stands for visual appearance and beauty while refinement is for reliable, true display. Fig. 34. Enhancement method stages

27 98 Advanced Image Acquisition, Processing Techniques and Applications binary erosion dilation negative Table 3. Steps of refinement stage opening negative Final 9.2 Binarization Thresholding techniques and algorithms Thresholding, is a binary contrast enhancement technique, that provides a simple means of defining the boundaries of objects that appear on a contrasting background. The threshold range is specified by a low value and a high value (Leedham, 2003, Solihin, 1999), see fig. 37. For the binarization of images many threshold algorithms, (global, local and adaptive), have been proposed to separate foreground from background objects (Yang, 2000). We have chosen Otsu s (Otsu, 1979), Niblack s (Niblack, 1986), Sauvola s and Bernsen s binarization methods (Sauvola, 2000) are used to compare their results on Byzantine textual images taken from the Holy Monastery of Dousiko, Pylh, near Meteora, Trikala, Thessaly, Greece. Global thresholding 1, if f ( x, y) T gxy (, ) 0, otherwise If T the global threshold of image f(x,y) and the g(x,y) is the thresholding result. Otsu s optimal threshold method minimizes the class variance of the two classes of pixels.threshold selection is absolute, conventional, optimal, automatic, adaptive, nonparametric, parametric, etc. 9.3 Lighting conditions Light text is harder to read than dark text. Responses to light text are slower and less accurate for a given contrast. Letters recognition is based on component features. Optical density is the amount of light reflected or transmitted on a logarithmic scale. Vectorial processing depends on the exposure light conditions. (sun, daylight, lamp, cool white fluorescent lighting, incandescent lamp, flash, candle, etc), illumination, non uniformity, low contrast, degradation, shadows etc. The camera and lighting should be calibrated, each channel is processed separately, stray light reduce the measured dynamic range while lighting should be even, aligned, glare-free with variation less than ±5%, with gray surround and no light behind the camera and stable background intensity to flatten image tones; two lamps at least with incident angle of and auto-exposure cameras compensate glare in the dark zones. Sparkle filter adds sparkles to our image, Lens flare filter gives the impression that sun hit the shot object and creates reflection effect. 3D Effect filter highlights perspective, Drop shadow filter adds a drop-shadow to the image, see fig. 35.

28 Digital Restoration by Denoising and Binarization of Historical Manuscripts Images 99 Table 4. Lighting conditions and effects on a Byzantine page Gradient flare or supernova filter creates random glow, rays, opacity Lighting effects filter simulates the light up of a spot, with no shadows and details in dark zones, transparency, background, direction, color, intensity, position, reflections by objects. Fig. 35. Lighting effects filter Changes in illumination, or local shadows do not provide global threshold, see fig. 36. (a) (b) (c) Fig. 36. Global threshold (a) grayscale image (b) T=100 (c) T=150 Fig. 37. Levels of thresholding and quality of results

29 100 Advanced Image Acquisition, Processing Techniques and Applications Local thresholding Niblack s method T(x,y)=m(x,y)+k*s(x,y) k=-0.2 where m(x,y) and s(x,y) are the average of a local area and the standard deviation.. A window size 15-by-15 suppresses the noise in the image, but preserves local details Sauvola s method is an adaptive threshold method, with k=0.1 and R=128. (, ) Txy (, ) mxy (, ) 1 k 1 sxy R Bernsen s method where Z max and Z min are maximum/minimum intensity and works in high contrast C(x,y) dependent on k and on the window size n. Threshold produces ghosts. Z Txy (, ) max max Z 2 Cxy (, ) Z Z min min 9.4 Thresholding results Binarization is applied to all document image categories. Image focusing, sharpness and clarification on the handwritten characters (Kavallieratou, 2002), and texture was compared with the original ones, see Table 5. The binarization, based on adaptive global /local thresholding, is efficient in image digitalisation and works best on high resolution images. JPEG file formats need the least computational effort to be processed. Documents Image Category / Binarization Bernsen Niblack Otsu Sauvola GOOD CONDITION BEST BEST BEST BEST SPOTS and STAINS BAD GOOD BAD BEST SHADOWS or WRINKLES BAD BEST BAD BEST INK SEEKING from other SIDE BAD GOOD BAD BEST THIN STROKES of PEN BAD BAD GOOD BAD RED coloured CHARACTERS BEST GOOD GOOD GOOD Table 5. Results from combination of Wiener filter 5x5 with binarization methods for image category Thresholding techniques applied to classified byzantine documental images reveal the comparative effect of combined filtering and binarization. Niblack s and Sauvola s methods produce efficient results in almost all categories except the category of thin strokes of pen in which global Otsu s method has the best results on the produced binary images (Niblack, 1993). Bernsen s method produced best results in manuscripts with characters with spots and stains and red coloured characters. Our

30 Digital Restoration by Denoising and Binarization of Historical Manuscripts Images 101 post-binarization refinement improves the image quality, the appearance of the binary images and text readability, clarifies the background area, especially in documents with red ink characters and line gaps or holes. Refinement consists of the successive erosion followed by dilation operation, and opening on the negative image, see fig. 38, 39. original document image with spot original document image with illumination shadow with ink seeking from other side, transparent background binary image binary image Sauvola method with Sauvola s with Sauvola s binary image method after 5x5Wiener filter method after 5x5Wiener filter after Wiener filter 5-by-5 original Document image with thin strokes of pen original Document image with characters with red ink detail of image with black dots before / after refinement step binary image with Sauvola s method after 5x5Wiener filter Table 6. Document image before and after binarization binary image with Otsu s method after Wiener filter 5x5 image with holes on characters before/after refinement step Fig. 38. Equalize and Negative or Invert Value and White balance for thresholding Fig. 39. Colorify / Color enhance and threshold

31 102 Advanced Image Acquisition, Processing Techniques and Applications 10. Compression Byzantine images are saved as RAW file, TIFF, or high quality JPEG. Raw images can be converted to JPEG (maximum quality), TIFF (without LZW compression), or PNG and removes redundancy. TIFF is the standard print industry format. We crop the images to minimize edge effects. RAW to TIFF, JPEG, etc converters perform additional functions such as add gamma curve and an additional tonal response curve, they reduce noise and sharpen the image. Compression tools (lossless and lossy) for images are included, depending on streaming (capture, store, and transfer (via a network) images) vs relative CPU, memory usage, channel demands, and storage requirements. Different compression algorithms are available such as whitespace compression, Run-Length Encoding (RLE), Huffman Encoding, Lempel Ziv-Compression, etc. A special quality of word-based Huffman compressed text is that it does not needs to undergo decompression to be searched by standard searching algorithms, so would lose none of the algorithm searchability. Compression problems include nonlinear quantization, colour channels, etc. JPEGs compress the file or the colour channels in ways that the eye is unable to easily detect, i.e. the structural detail is preserved, but when high levels of compression are applied increasingly fine detail is sacrificed, and some corruption will be detectable at higher magnification. Compression that gives rise to artifacts, corruption of the image, is lossy compression, and once the clarity of your image is lost it cannot be restored Database Organizing valuable or impossible to access fragile images from Byzantine sources in a database, (Gatos, 2004) is a powerful way to communicate and distribute them on the web by handling a massive quantity of images. Content-Based searching (texture/pattern, shape, color, orientation, and layout or a combination) of Large Image Databases is impractical and time consuming (Date, 2002). The relational database organize and manage such information, create virtual classifications, virtual folders, and interact with images, and metadata. Most frequently requested and computationally intensive jobs should be preprocessed, so that will be quickly hit, while others at the time of request. Utilities and software tools (middleware) facilitate organization for efficient access (searching, browsing, and retrieval), manipulate, enhance, and annotate existing information. Multimedia information contains an enormous amount of embedded information. An abstract function operation is edge detection or thresholding. The semi-compressed domain is convenient since it is an intermediate form that compressed video frames and images must pass through during decompression. A Byzantine manuscript consists of hundreds of pages of high fidelity images where each image is MB or larger; existing tools are not designed to display / search / browse massive digitized documents. Multimedia information is stored at multiple resolutions, and the appropriate level of resolution is selected and transferred automatically based on parameters such as the speed of the link. It is increasingly difficult to ask a spreadsheet combined questions and we need to normalize the database rows/columns referred to as attributes. Database normalization iteratively divides large tables into smaller, enhances database consistency, reduces redundant data and ensures data dependencies, speeds up server performance with faster sorting and indexing (Date, 1999, Picard, 1993).

32 Digital Restoration by Denoising and Binarization of Historical Manuscripts Images 103 Fig. 40. Spreadsheet images acquisition classification scheme Classification We classified byzantine images according to their content, i.e. old handwriting, (Greek) manuscript (varying in types, size, color, format and level of noise, capital /lower case letters), document images and photos, byzantine music symbols, etc. Historical documents are high / low contrast, colour / grayscale, totally/partially degraded or damaged, paper image condition, with red ink characters and line gaps or holes, transparent, with transparent objects, transparent background, simple / complex, text / graphics highly mixed, etc (Foley, 1990). Text mining is not information retrieval, extraction, categorization, because they do not generate new information but it involve new discoveries through analysis of a text, i.e. uncover a new relationship. There is always a risk of missing, or misclassifying. We wish to optimize subjective impression and readability perception. Text readability increases by text contrast, background contrast, and relative text contrast (text contrast divided by background contrast). A software classifier can automate processing per document class assisted by a training database for the sorting system composed of images that have distinct differences Suggestions for further work Documents image restoration, binarization, filtering and processing is an issue of continuous researching. Most of the historical documents images, in libraries and museums, can be acquired and stored dynamically in computers, in digital format for preservation, storage, computation, reproduction, visualization, interpretation and recognition. The proposed technique investigated for optimal methods for every image type, among the existing methods, the image noise and the paper conditions. We investigated for a universally efficient method for all the images categories by focusing on best thresholding value for every pixel area in the image, i.e. a combination of global and local methods structured into processing levels. Potential application fields include the automation of the combined binarization-filtering procedure and the extension of the method to a wider area of documental and similar or non-documental images. An image typically goes through a series of transformations that extract information from the image or compute new information based on the image; this sequence can be monitored and automated through an Expert System.

33 104 Advanced Image Acquisition, Processing Techniques and Applications 11. Conclusion Although excellent image processing tools and techniques exist we either do not use them efficiently in application fields, or in an intelligent way (GIMP, 2011, Mathworks, 2011). Errors classification in old documents background, text, stamps and images, image processing by experts or an expert system assisted by image segmentation techniques could reveal lost details. The purpose of our work on denoising and binarization was to introduce an innovative sequential procedure for digital image acquisition of historical documents including image preparation, image type classification according to their condition and their spatial structure, global and local features or both, including document image data mining. Image processing pixel alterations, allow one-pass iterations only by near neighborhood of alteration reprocessing algorithms. Algorithm complexity analysis is O(N3), while computational effort and execution time needed is overcome by parallel computational machines. In handwritten documents text orientation, skew, skew detection time and skew reconstruction time are critical parameters. The estimated results for each class of images and each method are further enhanced by an innovative image refinement technique and a formulation of a class proper method. Our work tends to focus mostly on Images Digital Restoration rather than on Binarization. Due to the dynamic research on the field, comparison of methods and techniques is continuous. Method efficiency, universality, versatility, flexibility and robustness is straightforward on any historical document and other cases, but selection or combination of appropriate algorithm (no single algorithm works well for all types of images) is needed. Compared to the image enhancement method, the image classification method is more text / image characteristic-oriented. It highly depends on the images to be processed, or saying in another way, the historical document to be investigated. There is no ideal method working for every case. There is not a single suitable method that can be applied to all types of images. 12. Appendix I. Properties of paper Property Comment Meaning Range Standard Print quality appearance properties roughness, gloss, ink absorption, whiteness, brightness Printability Readability Basis Weight or Grammage: dot reproduction/gain, print gloss, hue shift and print uniformity true reproduction of original artwork Good printability, compressibility, absorbency and ink hold out give good printing and hand writing. ink to paper contrast most fundamental property of paper weight of paper per unit area TAPPI T 410, SCAN P6, DIN53104 & ISO: BSENISO536

34 Digital Restoration by Denoising and Binarization of Historical Manuscripts Images 105 Bulk (cubic centimetre/g) = Thickness (mm)* Basis Weight (g/m 2 ) * 1000 volume or thickness in relation to weigh reciprocal of density TAPPI T 500, SCAN P7 DIN53105, ISO534, BS: ENISO20534 Decrease in bulk/ increase in density makes the sheet smoother, glossier, less opaque, darker, lower in strength for printing bible Caliper or Thickness Curl Stresses that are introduced into the sheet during manufacture and use how bulky or dense paper is Paper curl is a deviation of a sheet from flat form range from 70 GSM onwards TAPPI T 411 TAPPI T 466 & T520 There are three basic types of curl, mechanical, structural and moisture curl; one side of the sheet pick up more moisture Dimensional Stability dimensional changes cause undesirable cockling and curling All papers expand with increased moisture content and contract with decreased moisture content, but the rate and extent of changes vary with different papers. Moisture 2-12% ISO 287 Porosity Smoothness Moisture varies depending on relative humidity, type of pulp used, degree of refining and chemical used. Most properties change as a with moisture content. Very low porosity or coated on one side or wax pick gives resistance to grease and moisture. total connecting air voids both vertical and horizontal, ability of fluids, to penetrate the paper structure Paper is highly porous, contains up to 70% air Porosity is an indication of absorptivity, the ability to accept ink or water roughness, levelness, compressibility, finish, appearance, pattern surface contour of paper Smoothness for writing, ease of travel of the pen over the paper, gives eye appeal as a rough paper is unattractive. Permanence Optical properties Brightness Whiteness for readability and opacity degree to which paper resists deterioration over time. Balanced white sheets have a yellowish cast but we perceive sheet with a bluish to be whiter % reflectance of blue light at a wavelength TAPPI/GE and ISO Whiter sheets reflect equally red, green, blue light, the visual spectrum

35 106 Advanced Image Acquisition, Processing Techniques and Applications Color: quality of light, viewed under a different light source hue, saturation, darkness or lightness). aesthetic value Gloss Gloss and smoothness diffusely reflected light TAPPI T 480 Opacity Sizing / Cobb Dirt Content sheet light absorbed, both sides printed the ability of fluids,, to penetrate the structure of pap visible to the eye such as bark, undigested wood, pitch, rust, plastic, etc light not passing through a sheet the writing ink go into the paper instantly and dry dirt specks, unwanted foreign particle Pin Holes Imperfections looking through water-repellent materials (rosin, wax, gelatinous) change reflected or transmitted light ISO 2471 and TAPPI T425. Other properties are Temperature and Humidity, Conditioning of Paper, Wire side and Felt side, Strength Properties, Surface Strength, Compressibility, Resiliency, Stiffness, etc. Certain properties such as smoothness, texture and ink absorbency differ between wire and felt side. Paper types include alkaline paper, antique paper, art paper, Bible paper, General Writing paper, etc. 13. Acknowledgements We would like to thank: 1. The Department of Computer Science Technology & Telecommunications, TEI Larisa 2. Holy Monastery Dousiko, Pylh near Meteora, Greece for Codices 1611 AD 3. Professor N.Papamarkos for software, References [1] Adams, A, The Camera. Bulfinch Press, 1995 [2] Blinn, James F. "Simulation of Wrinkled Surfaces", Computer Graphics, Vol. 12 (3), pp SIGGRAPH-ACM, August 1978 [3] Boyle R. and R. Thomas Computer Vision: A First Course, Blackwell Scientific Publications, 1988, Chap. 4. [4] Canon Europa N.V. and Canon Europe Ltd, Digital SRL Camera "5D", , Digital_SLR/EOS_5D/index.asp. [5] Date C.J., Hugh Darwen, Nikos Lorentzos. Temporal Data and the Relational Model. Morgan Kaufmann (2002), p. 176 [6] Date C.J. An Introduction to Database Systems. Addison-Wesley (1999), p. 290 [7] Davies E. Machine Vision: Theory, Algorithms and Practicalities, Academic Press, 1990, Chap. 4. [8] D Zmura M., Colantoni P., Knoblauch K., Laget B. (1997). Color transparency. Perception, 26, [9] [GIMP] GIMP - The Gnu Image Manipulation Program

36 Digital Restoration by Denoising and Binarization of Historical Manuscripts Images 107 [10] Foley and van Dam, et al, Computer Graphics, Principles and Practice, Copyright 1990 Addison Wesley. Addison Wesley. 2nd Ed. (Addison Wesley, 1990) [11] B. Gatos, K. Ntzios, I. Pratikakis, S. Petridis, T. Konidaris and S. J. Perantonis, A segmentation free recognition technique to assist old Greek handwritten manuscript OCR, IAPR Workshop on Document Analysis systems (DAS 2004), Lecture Notes in Computer Science (3163), Florence, Italy, September 2004, pp [12] B. Gatos, I. Pratikakis, S. J. Perantonis, Locating Text in Historical Collection Manuscripts, Lecture Notes on AI, SETN 2004, pp [13] Gonzalez, C.R. and E.R. Woods, "Digital Image Processing", 2nd ed, 2002, Prentice-Hall Inc, pp [14] Gupta A. et al, Enhancement of Old Manuscript Images, Proceeding ICDAR '07 Proceedings of the Ninth International Conference on Document Analysis and Recognition - Vol 2 IEEE Computer Society, Washington, USA 2007, ISBN: [15] Hunt R.W.G, The Reproduction of Colour in Photography, Printing and Television, Fountain Press, Tolworth, England, 5 th edition, 2001 [16] Kapur, J., P.K. Sahoo, and A.K.C. Wong, "A new method for gray-level picture. Thresholding using the Entropy of the Histogram", Computer Vision Graphics and Image Processing, 1985, pp [17] E. Kavallieratou, N. Fakotakis, G. Kokkinakis, Handwritten character recognition based on structural characteristics, 16th International Conference on Pattern Recognition, 2002, pp [18] E. Kavallieratou N.Fakotakis G Kokkinakis, New algorithms for skewing correction and slant removal on word-level, Proc. IEEE, 1999, pp [19] Knoblauch K., Arditi A., Szlyk J. (1991). Effects of chromatic and luminance contrast on reading. Journal of the Optical Society of America A, 8, [20] Leedham, CG, et al. "Comparison of some Thresholding Algorithms for Text /Background Segmentation in Difficult Document Images", Proceedings of 7 th International Conference on Document Analysis & Recognition, 2003, IEEE [21] Legge G., Pelli D., Rubin G., Schleske M, 1985, Psychophysics of reading. I. Normal vision. Vision Research, 25, [22] MathWorks Inc., "Image Processing Toolbox - User Guide", 2011 [23] Motwani, M., C., et al. "Survey of Image Denoising Techniques", in Proceedings of GSPx, 2004, Santa Clara Convention Center, Santa Clara, CA [24] Niblack, W., "An Introduction to Digital Image Processing" 1986, Prentice Hall, pp [25] Niblack, W. et al The QBIC project: querying images by content using color, texture, and shape. SPIE 1908:173-81, February [26] Otsu, N., "A threshold selection method from gray-level histograms", IEEE Trans. Systems, Man, and Cybernetics, vol. 9 (no. 1), pp [27] Papamarkos, N., "Digital Processing and Image Analysis", 2001, Athens, Giourdas [28] Picard, R. W. and Kabir, T Finding similar patterns in large image databases. [29] Ren Ng, Digital Light Field Photography, a dissertation submitted to the department of computer science of Stanford University, in partial fulfilment of the requirements for the degree of Doctor of Philosophy, July 2006

37 108 Advanced Image Acquisition, Processing Techniques and Applications [30] Sauvola, J. and M. Pietikainen, "Adaptive document image binarization", Pattern Recognition 33, 2000, pp [31] Solihin, Y. and C.G. Leedham, "Integral Ratio: A New Class of Global Thresholding Techniques for Handwriting images", IEEE Trans. on PAMI, 1999, vol 21 (no 8), pp [32] Sonka, M., V. Hlavac, and R. Boyle, "Image Processing, Analysis and Machine Vision", [33] Ventzas, D., "Edge Detection Techniques in the Industry", Advances in Modelling & Analysis, Series B, vol. 29, No. 2, pp , Winter , AMSE, [34] Yang, Y. and H. Yan, "An Adaptive logical method for binarization of degraded document images", Pattern recognition 33, 2000, pp [35] Yanowitz, D.L. and A.M. Bruckstein, "A new Method for image segmentation", Computer Vision Graphics and Image Processing, 1989, vol.46 (no 1), pp [36] Zhang, Z. and C. Tan, "Restoration of images scanned from thick bound documents", in proceedings of International Conference on Image Processing 2001, Vol 1, 2001, pp [37] [38] Data fusion web, Nov 2007 [39]

38 Advanced Image Acquisition, Processing Techniques and Applications I Edited by Dr. Dimitrios Ventzas ISBN Hard cover, 170 pages Publisher InTech Published online 14, March, 2012 Published in print edition March, 2012 "Advanced Image Acquisition, Processing Techniques and Applications" is the first book of a series that provides image processing principles and practical software implementation on a broad range of applications. The book integrates material from leading researchers on Applied Digital Image Acquisition and Processing. An important feature of the book is its emphasis on software tools and scientific computing in order to enhance results and arrive at problem solution. How to reference In order to correctly reference this scholarly work, feel free to copy and paste the following: Dimitrios Ventzas, Nikolaos Ntogas and Maria-Malamo Ventza (2012). Digital Restoration by Denoising and Binarization of Historical Manuscripts Images, Advanced Image Acquisition, Processing Techniques and Applications I, Dr. Dimitrios Ventzas (Ed.), ISBN: , InTech, Available from: InTech Europe University Campus STeP Ri Slavka Krautzeka 83/A Rijeka, Croatia Phone: +385 (51) Fax: +385 (51) InTech China Unit 405, Office Block, Hotel Equatorial Shanghai No.65, Yan An Road (West), Shanghai, , China Phone: Fax: